Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 646 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4567. Min Range: -3.4567
Max Act: 3.4567. Min Act: -0.1700
Data Index: 1540459 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4567. Min Range: -3.4567
Max Act: 3.3155. Min Act: -0.1700
Data Index: 6463574 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4567. Min Range: -3.4567
Max Act: 3.2998. Min Act: -0.1700
Data Index: 186369 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4567. Min Range: -3.4567
Max Act: 3.2527. Min Act: -0.1700
Data Index: 223812 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4567. Min Range: -3.4567
Max Act: 3.2213. Min Act: -0.1700
Data Index: 4840991 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4567. Min Range: -3.4567
Max Act: 3.2213. Min Act: -0.1700
Data Index: 8026903 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4567. Min Range: -3.4567
Max Act: 3.2213. Min Act: -0.1700
Data Index: 7770224 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4567. Min Range: -3.4567
Max Act: 3.2213. Min Act: -0.1700
Data Index: 390033 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4567. Min Range: -3.4567
Max Act: 3.2370. Min Act: -0.1700
Data Index: 2497927 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4567. Min Range: -3.4567
Max Act: 3.2056. Min Act: -0.1700
Data Index: 6225023 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4567. Min Range: -3.4567
Max Act: 3.1741. Min Act: -0.1700
Data Index: 7071378 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4567. Min Range: -3.4567
Max Act: 3.1741. Min Act: -0.1700
Data Index: 1759763 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4567. Min Range: -3.4567
Max Act: 3.1898. Min Act: -0.1700
Data Index: 554804 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4567. Min Range: -3.4567
Max Act: 3.1584. Min Act: -0.1700
Data Index: 4489597 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4567. Min Range: -3.4567
Max Act: 3.1426. Min Act: -0.1700
Data Index: 8574519 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4567. Min Range: -3.4567
Max Act: 3.1584. Min Act: -0.1700
Data Index: 5722470 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4567. Min Range: -3.4567
Max Act: 3.1426. Min Act: -0.1700
Data Index: 4678108 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4567. Min Range: -3.4567
Max Act: 3.1269. Min Act: -0.1700
Data Index: 4445218 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4567. Min Range: -3.4567
Max Act: 3.1111. Min Act: -0.1700
Data Index: 1096446 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4567. Min Range: -3.4567
Max Act: 3.1111. Min Act: -0.1700
Data Index: 2232943 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19